basic_wnut

This model is a fine-tuned version of distilbert-base-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:

• Loss: 0.3181
• Precision: 0.5470
• Recall: 0.3994
• F1: 0.4617
• Accuracy: 0.9469

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-07
• train_batch_size: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	27	0.2984	0.5557	0.3930	0.4604	0.9463
No log	2.0	54	0.2991	0.5547	0.3902	0.4581	0.9462
No log	3.0	81	0.2993	0.5557	0.3930	0.4604	0.9463
No log	4.0	108	0.3011	0.5550	0.3883	0.4569	0.9461
No log	5.0	135	0.3015	0.5532	0.3902	0.4576	0.9462
No log	6.0	162	0.2997	0.5467	0.3957	0.4591	0.9463
No log	7.0	189	0.2997	0.5487	0.3967	0.4605	0.9462
No log	8.0	216	0.2998	0.5439	0.3957	0.4582	0.9463
No log	9.0	243	0.3024	0.5501	0.3920	0.4578	0.9462
No log	10.0	270	0.3021	0.5470	0.3939	0.4580	0.9462
No log	11.0	297	0.3027	0.5471	0.3930	0.4574	0.9463
No log	12.0	324	0.3023	0.5453	0.3957	0.4586	0.9463
No log	13.0	351	0.3028	0.5481	0.3957	0.4596	0.9463
No log	14.0	378	0.3028	0.5467	0.3957	0.4591	0.9463
No log	15.0	405	0.3034	0.5444	0.3976	0.4596	0.9464
No log	16.0	432	0.3040	0.5431	0.3967	0.4585	0.9464
No log	17.0	459	0.3068	0.5484	0.3939	0.4585	0.9464
No log	18.0	486	0.3077	0.5501	0.3920	0.4578	0.9466
0.0203	19.0	513	0.3057	0.5434	0.3948	0.4573	0.9463
0.0203	20.0	540	0.3078	0.5494	0.3920	0.4575	0.9464
0.0203	21.0	567	0.3074	0.5517	0.3957	0.4609	0.9465
0.0203	22.0	594	0.3070	0.5499	0.3985	0.4621	0.9465
0.0203	23.0	621	0.3065	0.5497	0.3994	0.4627	0.9465
0.0203	24.0	648	0.3064	0.5450	0.3985	0.4604	0.9464
0.0203	25.0	675	0.3077	0.5467	0.3957	0.4591	0.9465
0.0203	26.0	702	0.3070	0.5458	0.3976	0.4601	0.9464
0.0203	27.0	729	0.3084	0.5494	0.3967	0.4607	0.9466
0.0203	28.0	756	0.3086	0.5487	0.3967	0.4605	0.9465
0.0203	29.0	783	0.3087	0.5486	0.3976	0.4610	0.9466
0.0203	30.0	810	0.3087	0.5444	0.3976	0.4596	0.9464
0.0203	31.0	837	0.3108	0.5510	0.3957	0.4606	0.9466
0.0203	32.0	864	0.3107	0.5494	0.3967	0.4607	0.9466
0.0203	33.0	891	0.3097	0.5429	0.3985	0.4596	0.9466
0.0203	34.0	918	0.3114	0.5493	0.3976	0.4613	0.9466
0.0203	35.0	945	0.3100	0.5430	0.3976	0.4591	0.9465
0.0203	36.0	972	0.3100	0.5442	0.3994	0.4607	0.9466
0.0203	37.0	999	0.3099	0.5428	0.3994	0.4602	0.9466
0.0177	38.0	1026	0.3109	0.5450	0.3985	0.4604	0.9465
0.0177	39.0	1053	0.3117	0.5488	0.3957	0.4599	0.9466
0.0177	40.0	1080	0.3119	0.5493	0.3976	0.4613	0.9466
0.0177	41.0	1107	0.3129	0.5528	0.3976	0.4625	0.9468
0.0177	42.0	1134	0.3124	0.5473	0.3967	0.4600	0.9467
0.0177	43.0	1161	0.3128	0.55	0.3976	0.4615	0.9468
0.0177	44.0	1188	0.3132	0.5514	0.3976	0.4620	0.9469
0.0177	45.0	1215	0.3119	0.5457	0.3985	0.4606	0.9467
0.0177	46.0	1242	0.3115	0.5436	0.3985	0.4599	0.9467
0.0177	47.0	1269	0.3127	0.5460	0.3957	0.4589	0.9466
0.0177	48.0	1296	0.3132	0.5474	0.3957	0.4594	0.9467
0.0177	49.0	1323	0.3137	0.5469	0.3948	0.4586	0.9467
0.0177	50.0	1350	0.3147	0.5510	0.3957	0.4606	0.9468
0.0177	51.0	1377	0.3133	0.5459	0.3967	0.4595	0.9468
0.0177	52.0	1404	0.3129	0.5436	0.3985	0.4599	0.9468
0.0177	53.0	1431	0.3138	0.5431	0.3967	0.4585	0.9467
0.0177	54.0	1458	0.3141	0.5437	0.3976	0.4593	0.9468
0.0177	55.0	1485	0.3141	0.5431	0.3967	0.4585	0.9467
0.0162	56.0	1512	0.3156	0.5473	0.3967	0.4600	0.9469
0.0162	57.0	1539	0.3147	0.5463	0.3994	0.4615	0.9469
0.0162	58.0	1566	0.3150	0.5450	0.3985	0.4604	0.9469
0.0162	59.0	1593	0.3154	0.5429	0.3985	0.4596	0.9468
0.0162	60.0	1620	0.3165	0.5486	0.3976	0.4610	0.9468
0.0162	61.0	1647	0.3150	0.5435	0.3994	0.4605	0.9468
0.0162	62.0	1674	0.3161	0.5450	0.3985	0.4604	0.9468
0.0162	63.0	1701	0.3159	0.5430	0.3976	0.4591	0.9467
0.0162	64.0	1728	0.3168	0.5458	0.3976	0.4601	0.9467
0.0162	65.0	1755	0.3168	0.5471	0.3985	0.4611	0.9468
0.0162	66.0	1782	0.3160	0.5429	0.3985	0.4596	0.9467
0.0162	67.0	1809	0.3166	0.5450	0.3985	0.4604	0.9467
0.0162	68.0	1836	0.3172	0.5457	0.3985	0.4606	0.9468
0.0162	69.0	1863	0.3168	0.5476	0.3994	0.4620	0.9468
0.0162	70.0	1890	0.3167	0.5470	0.3994	0.4617	0.9468
0.0162	71.0	1917	0.3167	0.5449	0.3994	0.4610	0.9468
0.0162	72.0	1944	0.3153	0.5439	0.4022	0.4624	0.9469
0.0162	73.0	1971	0.3155	0.5439	0.4022	0.4624	0.9469
0.0162	74.0	1998	0.3160	0.5428	0.3994	0.4602	0.9468
0.0153	75.0	2025	0.3167	0.5435	0.3994	0.4605	0.9469
0.0153	76.0	2052	0.3171	0.5449	0.3994	0.4610	0.9469
0.0153	77.0	2079	0.3176	0.5463	0.3994	0.4615	0.9469
0.0153	78.0	2106	0.3177	0.5463	0.3994	0.4615	0.9469
0.0153	79.0	2133	0.3172	0.5449	0.3994	0.4610	0.9469
0.0153	80.0	2160	0.3171	0.5443	0.3985	0.4601	0.9469
0.0153	81.0	2187	0.3171	0.5443	0.3985	0.4601	0.9469
0.0153	82.0	2214	0.3173	0.5457	0.3985	0.4606	0.9469
0.0153	83.0	2241	0.3174	0.5450	0.3985	0.4604	0.9468
0.0153	84.0	2268	0.3174	0.5436	0.3985	0.4599	0.9467
0.0153	85.0	2295	0.3170	0.5442	0.3994	0.4607	0.9467
0.0153	86.0	2322	0.3172	0.5449	0.3994	0.4610	0.9468
0.0153	87.0	2349	0.3181	0.5456	0.3994	0.4612	0.9468
0.0153	88.0	2376	0.3179	0.5463	0.3994	0.4615	0.9468
0.0153	89.0	2403	0.3181	0.5470	0.3994	0.4617	0.9469
0.0153	90.0	2430	0.3179	0.5470	0.3994	0.4617	0.9469
0.0153	91.0	2457	0.3181	0.5470	0.3994	0.4617	0.9469
0.0153	92.0	2484	0.3182	0.5463	0.3994	0.4615	0.9468
0.0145	93.0	2511	0.3182	0.5470	0.3994	0.4617	0.9469
0.0145	94.0	2538	0.3181	0.5470	0.3994	0.4617	0.9469
0.0145	95.0	2565	0.3182	0.5463	0.3994	0.4615	0.9468
0.0145	96.0	2592	0.3180	0.5470	0.3994	0.4617	0.9469
0.0145	97.0	2619	0.3180	0.5463	0.3994	0.4615	0.9469
0.0145	98.0	2646	0.3180	0.5463	0.3994	0.4615	0.9469
0.0145	99.0	2673	0.3181	0.5470	0.3994	0.4617	0.9469
0.0145	100.0	2700	0.3181	0.5470	0.3994	0.4617	0.9469

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0